{"id":"https://openalex.org/W4414322676","doi":"https://doi.org/10.1109/ecmr65884.2025.11163198","title":"UAV-VLN: End-to-End Vision Language guided Navigation for UAVs","display_name":"UAV-VLN: End-to-End Vision Language guided Navigation for UAVs","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414322676","doi":"https://doi.org/10.1109/ecmr65884.2025.11163198"},"language":"en","primary_location":{"id":"doi:10.1109/ecmr65884.2025.11163198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecmr65884.2025.11163198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 European Conference on Mobile Robots (ECMR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.21432","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074464161","display_name":"Pranav Saxena","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]},{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranav Saxena","raw_affiliation_strings":["Birla Institute of Technology and Science Pilani,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science Pilani,Goa,India","institution_ids":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nishant Raghuvanshi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]},{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nishant Raghuvanshi","raw_affiliation_strings":["Birla Institute of Technology and Science Pilani,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science Pilani,Goa,India","institution_ids":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034204619","display_name":"Neena Goveas","orcid":"https://orcid.org/0000-0002-5395-4962"},"institutions":[{"id":"https://openalex.org/I4210148827","display_name":"Birla Institute of Technology and Science, Pilani - Goa Campus","ror":"https://ror.org/046sh6j17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]},{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neena Goveas","raw_affiliation_strings":["Birla Institute of Technology and Science Pilani,Goa,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science Pilani,Goa,India","institution_ids":["https://openalex.org/I4210148827","https://openalex.org/I74796645"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":38.2211,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99798669,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.595300018787384},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5109000205993652},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4941999912261963},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.45100000500679016},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4255000054836273},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.3919000029563904},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3792000114917755},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616000175476074},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5909000039100647},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5153999924659729},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ecmr65884.2025.11163198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecmr65884.2025.11163198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 European Conference on Mobile Robots (ECMR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.21432","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.21432","pdf_url":"https://arxiv.org/pdf/2504.21432","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.21432","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.21432","pdf_url":"https://arxiv.org/pdf/2504.21432","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414322676.pdf","grobid_xml":"https://content.openalex.org/works/W4414322676.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2060303868","https://openalex.org/W2102160523","https://openalex.org/W2193145675","https://openalex.org/W2604579016","https://openalex.org/W2788239209","https://openalex.org/W2838655638","https://openalex.org/W2890902815","https://openalex.org/W2963037989","https://openalex.org/W2963800628","https://openalex.org/W2979727876","https://openalex.org/W3034758614","https://openalex.org/W3039927678","https://openalex.org/W3100923070","https://openalex.org/W3109085430","https://openalex.org/W3203663566","https://openalex.org/W4213147678","https://openalex.org/W4312420092","https://openalex.org/W4389666115","https://openalex.org/W4402353987","https://openalex.org/W4402726789","https://openalex.org/W4406940147"],"related_works":[],"abstract_inverted_index":{"A":[0],"core":[1],"challenge":[2],"in":[3,14,69,94,110,169],"AI-guided":[4],"autonomy":[5],"is":[6],"enabling":[7],"agents":[8],"to":[9,48,79,153,155],"navigate":[10],"realistically":[11],"and":[12,64,89,113,124,146,158,172,185],"effectively":[13],"previously":[15],"unseen":[16],"environments":[17,159],"based":[18],"on":[19],"natural":[20,56],"language":[21,57],"commands.":[22],"We":[23],"propose":[24],"UAV-VLN,":[25],"a":[26,85,130],"novel":[27,156],"end-to-end":[28],"Vision-Language":[29],"Navigation":[30],"(VLN)":[31],"framework":[32,128],"for":[33,182],"Unmanned":[34],"Aerial":[35],"Vehicles":[36],"(UAVs)":[37],"that":[38,134],"seamlessly":[39],"integrates":[40],"Large":[41],"Language":[42],"Models":[43],"(LLMs)":[44],"with":[45,117,138,160],"visual":[46,62,139],"perception":[47],"facilitate":[49],"human-interactive":[50],"navigation.":[51],"Our":[52,164],"system":[53],"interprets":[54],"free-form":[55],"instructions,":[58,112],"grounds":[59],"them":[60],"into":[61],"observations,":[63],"plans":[65],"feasible":[66],"aerial":[67],"trajectories":[68],"diverse":[70,144],"environments.UAV-VLN":[71],"leverages":[72],"the":[73,95,101,127,176],"common-sense":[74],"reasoning":[75],"capabilities":[76],"of":[77,178],"LLMs":[78],"parse":[80],"high-level":[81],"semantic":[82],"goals,":[83],"while":[84],"vision":[86],"model":[87],"detects":[88],"localizes":[90],"semantically":[91],"relevant":[92],"objects":[93],"environment.":[96],"By":[97],"fusing":[98],"these":[99],"modalities,":[100],"UAV":[102,187],"can":[103],"reason":[104],"about":[105],"spatial":[106],"relationships,":[107],"disambiguate":[108],"references":[109],"human":[111],"plan":[114],"context-aware":[115],"behaviors":[116],"minimal":[118,161],"task-specific":[119,162],"supervision.":[120],"To":[121],"ensure":[122],"robust":[123],"interpretable":[125],"decision-making,":[126],"includes":[129],"cross-modal":[131],"grounding":[132],"mechanism":[133],"aligns":[135],"linguistic":[136],"intent":[137],"context.We":[140],"evaluate":[141],"UAV-VLN":[142],"across":[143],"indoor":[145],"outdoor":[147],"navigation":[148],"scenarios,":[149],"demonstrating":[150],"its":[151],"ability":[152],"generalize":[154],"instructions":[157],"training.":[163],"results":[165],"show":[166],"significant":[167],"improvements":[168],"instruction-following":[170],"accuracy":[171],"trajectory":[173],"efficiency,":[174],"highlighting":[175],"potential":[177],"LLM-driven":[179],"vision-language":[180],"interfaces":[181],"safe,":[183],"intuitive,":[184],"generalizable":[186],"autonomy.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}